From a81685628dc3b2077b69fb492f6e799f3c76525d Mon Sep 17 00:00:00 2001
From: Yuval Adam <yuv.adm@gmail.com>
Date: Mon, 11 Oct 2010 16:09:51 +0200
Subject: updated import script with pseudocode

---
 importutils/import.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/importutils/import.py b/importutils/import.py
index e2aa14a..491fb5b 100644
--- a/importutils/import.py
+++ b/importutils/import.py
@@ -1,9 +1,25 @@
+
+# 1. pre-condition : work by year, all files deployed on file system
+# 2. un-gzip all files (by default, into same directory, overriding .gz files)
+# 3. rename all TCSC files to TCSC.dmp (prepare for imp)
+# 4. for each TCSC.dmp file:
+#   4.1. call imp on each single file (guaranteed to be < ~300MB)
+#   4.2. for each table (need to create hard-coded list)
+#       4.2.1. SELECT * FROM table
+#       4.2.2. save aside, or throw into new db
+#   4.3. dump all tables (make room for next iteration)
+
+
 import os
 import sys
+import subprocess
 
 RAW_DATA_BASE_DIR = "/base/dir/location" # update this
 
 def importYear(year):
     yearDir = os.path.join(RAW_DATA_BASE_DIR, str(year))
-    print 
+    print yearDir
+    
+importYear(2005)
+
 
-- 
cgit v1.3.1